Search
65 articles for “F1 Score”
-
Textual Clues to Stress: A Machine Learning Approach
Abstract: Nowadays, numerous individuals utilize social media platforms to share tweets about their daily lives, which often reflect their mental well-being. Recognizing and managing stress is essential before it becomes a serious issue. Each day, a significant volume of informal messages is posted on discussion forums, blogs, and social networking sites. This study introduces a method for detecting stress using information gathered from social media, with a focus on Twitter. The …
Published in Journal of Computer Technology & Applications · Vol. 16, Issue 1, 2025 · pp. 72–76 Read article
-
From Space to Sea: Leveraging Satellite Technology for Monitoring Marine Debris
Abstract: Marine trash endangers ecosystems, so efficient detection is critical. This article describes a novel strategy for improving detection accuracy by integrating YOLOv7 instance segmentation with attention processes. Three models are evaluated: lightweight coordinate attention, the convolutional block attention module (CBAM) for spatial-channel focus, and the bottle neck transformer, which relies on self-attention. On an annotated satellite image dataset, CBAM has the greatest F1 scores in box recognition (77%) and mask …
Published in Research & Reviews : Journal of Space Science & Technology · Vol. 14, Issue 1, 2025 · pp. 1–9 Read article
-
Signal Feature Extraction and Machine Learning Techniques for Human Activity Recognition
Abstract: Human Activity Recognition (HAR) has emerged as a critical field of study with diverse applications in healthcare, fitness tracking, smart homes, and human-computer interaction. The aim of this research is to create an efficient HAR system through advanced techniques characterized by signal feature extraction and machine learning algorithms. The MEMS sensors are used appropriately during data mining to extract time-domain, frequency-domain, and statistical features, which are subsequently passed to the …
Published in Journal of Mobile Computing, Communications & Mobile Networks · Vol. 12, Issue 1, 2025 · pp. 24–41 Read article
-
Sustainable Cotton Crop Productivity through Precision Weed Detection: A Deep Learning-Based Approach with UAV Integration
Abstract: Weeds present a major challenge to crop productivity by competing with crops for vital resources, including water, sunlight, and nutrients, often resulting in significant yield reductions. On a global scale, weeds are responsible for approximately 13.2% of annual crop losses, a quantity sufficient to feed nearly one billion people. These invasive plants disrupt agricultural systems and adversely impact crop yields. Given their uneven distribution in fields, ground or aerial robots …
Published in Journal of Aerospace Engineering & Technology · Vol. 15, Issue 1, 2025 · pp. 19–26 Read article
-
Prediction of Customer Churn Using Machine Learning Classification Models
Abstract: Customer churn prediction is a critical task in both the telecommunication and medical industries, where retaining customers or patients is essential for ensuring long-term profitability and maintaining high-quality service. To address this, a range of machine learning models—including logistic regression, decision trees, random forests, gradient boosting machines, and support vector machines—were employed to accurately forecast churn behavior. Prior to model training, the dataset underwent thorough preprocessing, which included handling missing …
Published in Journal of Computer Technology & Applications · Vol. 16, Issue 2, 2025 · pp. 86–92 Read article
-
Algorithm for the prediction of cardiovascular disease (CVD)
Abstract: cardiovascular diseases (CVD) still claim a significant number of deaths globally and remain the number one killer with an annual death toll of nearly 17.9 million. While several medical advancements have been made, an early diagnosis is still hard to obtain, which often leads to worsening conditions and intricate treatment options. With the advancement of modern technology, Machine learning has demonstrated to be a miraculous tool which can greatly impact …
Published in Research and Reviews : A Journal of Immunology · Vol. 15, Issue 2, 2025 Read article
-
U-Net Based Approach for Automated Brain Tumor Classification
Abstract: Brain tumor detection and identification play vital roles in diagnostic procedures in the field of medicine, with the conventional analysis of MRI images requiring a lot of time and also subject to variability. The proposed study involves the use of a CNN-U-Net based approach for brain tumor detection and identification automatically. The study uses a database of 3,064 contrast-enhanced T1-weighted MRI images from 233 patients with the tumors of meningioma, …
Published in Research and Reviews: Journal of Oncology and Hematology · Vol. 14, Issue 2, 2025 Read article
-
Brain Tumor Detection Using RestNet50 Architecture
Abstract: This paper presents a novel deep learning model for brain tumor diagnosis from MRI scans on the basis of ResNet50 with some modifications. Optimizing the modified layers and pre-trained ResNet50 for improved diagnostic accuracy and reliability in real-world clinical settings is one of the key contributions of this paper. The model was trained on an extremely well-balanced data of 2,577 MRI scans, which were split equally among the tumor and …
Published in Current Trends in Signal Processing · Vol. 15, Issue 2, 2025 · pp. 1–13 Read article
-
Multimodal Disease Detection Using Deep Learning
Abstract: Artificial Intelligence (AI) is playing an increasingly pivotal role in modern healthcare, particularly in improving the speed and accuracy of disease detection. With the evolution of Machine Learning (ML), Deep Learning (DL), and high-performance computing, AI-based solutions are now capable of processing extensive medical datasets, ranging from patient records to diagnostic images, with remarkable efficiency. These systems offer immense potential for early intervention, improved clinical decision-making, and alleviating pressure on …
Published in Journal of Computer Technology & Applications · Vol. 16, Issue 2, 2025 · pp. 129–139 Read article
-
Enhancing Glaucoma Diagnosis with Deep Learning: A Study Using ResNet-50 and DenseNet-121
Abstract: Glaucoma is a leading cause of irreversible blindness worldwide, mainly resulting from progressive optic nerve damage, often related to elevated intraocular pressure. Early detection is essential to prevent vision loss, but traditional diagnostic methods rely on specialized equipment and trained professionals, making large-scale screening difficult. This study uses a publicly available fundus imaging dataset to explore the effectiveness of deep learning models for glaucoma detection. These datasets provide medical images, …
Published in International Journal of Brain Sciences · Vol. 2, Issue 2, 2025 · pp. 9–18 Read article
-
Efficient Machine Defect Detection with Sugeno Fuzzy Membership and GRU Networks for Robust Industrial Automation
Abstract: Machine fault detection is of immense significance in industrial automation to achieve efficient operations, reduced downtime, and reduced economic losses. Sugeno fuzzy logic and Gated Recurrent Unit (GRU) networks are used in this research to provide a new hybrid solution that addresses problems such as noisy data, evolving defect patterns, and real-time detection. To improve readability and reliability, the Sugeno fuzzy logic unit preprocesses fuzzy and uncertain input data into …
Published in Journal of Mechatronics and Automation · Vol. 12, Issue 2, 2025 · pp. 17–26 Read article
-
Ai-Driven Healthcare System for Enhanced Diagnosis and Patient Interaction
Abstract: Deep learning techniques are used in an AI-driven healthcare system to improve disease identification and medical picture analysis. Data collection, preprocessing, model training, and evaluation are all part of the system's systematic workflow. Various deep learning architectures, such as ResNet50, VGG-16, and U-Net, are employed for precise classification and segmentation of medical images. The approach incorporates advanced techniques such as optimization, transfer learning, and data augmentation to significantly enhance the …
Published in Research and Reviews: A Journal of Health Professions · Vol. 15, Issue 2, 2025 Read article
-
Timestamp Extraction and Log Classification Using Supervised Machine Learning: A Comparative Study
Abstract: In modern software systems, logs are vital for monitoring application behavior, diagnosing issues, and analyzing performance. Timestamps are especially important for sequencing events, identifying anomalies, and understanding system failures. However, detecting timestamps in logs is challenging due to inconsistent formatting across systems and the presence of timestamp-like strings in non-timestamp fields. Traditional rule-based methods often fail in such cases. This study proposes a supervised machine learning approach to accurately classify …
Published in Journal of Software Engineering Tools & Technology Trends · Vol. 12, Issue 3, 2025 · pp. 26–38 Read article
-
A Comprehensive Survey on Detection of Video Transitions
Abstract: Video shot boundary detection (SBD) is a fundamental task in the field of video processing and analysis. It plays a critical role in various video applications such as content-based video retrieval, video indexing, editing, summarization, and browsing. Identifying shot boundaries helps segment a continuous video stream into distinct shots, each representing a meaningful visual unit. This segmentation is essential for organizing and interpreting video data efficiently. This study provides an …
Published in Journal of Multimedia Technology & Recent Advancements · Vol. 12, Issue 3, 2025 · pp. 17–26 Read article
-
Quasi-Sobol-Based Optimization and Sigmoid Fuzzy Logic for Efficient Task Clustering in Decentralized Edge-Cloud Architectures
Abstract: Decentralized edge-cloud systems face a lot of issues in efficient task clustering, resource allocation, and real-time decision-making. Conventional methods mostly fail to work well under dynamic workloads and uncertain conditions. This study intends to optimize task clustering through quasi-Sobol-based optimization and Sigmoid Fuzzy Logic for resource allocation, enhancing decision-making accuracy and achieving efficiency in the system at the edge-cloud environment. A hybrid technique that has incorporated optimization via Quasi-Sobol sequences …
Published in Trends in Machine design · Vol. 12, Issue 2, 2025 · pp. 9–18 Read article
-
A Machine Learning Approach to Forecasting Outcomes in Limited Overs Cricket
Abstract: This study explores the application of machine learning techniques to forecasting outcomes in limited overs cricket matches, with a particular focus on One Day Internationals (ODIs). The research investigates how classification algorithms can be effectively utilized to analyze both contextual and dynamic factors that influence match results, including venue details, toss decisions, team strength, and historical performance records. By employing a structured methodology encompassing feature selection, data preprocessing, model training, …
Published in Recent Trends in Sports · Vol. 2, Issue 2, 2025 · pp. 09–19 Read article
-
Comparative Analysis of AI-Based Approach vs. Traditional Methods in Climate Modeling
Abstract: Climate modeling helps to predict the future of climate variations and human interference with environment. The traditional General Circulation Models (GCMs) are based on physics-derived mathematical equations but are very expensive in terms of computation. There are alternative ways to perform climate modeling in recent years with the rise and improvement of Artificial Intelligence (AI) based approaches in term of predictability, efficiency, and classification of extreme events compared to conventional. …
Published in Current Trends in Information Technology · Vol. 15, Issue 3, 2025 · pp. 26–32 Read article
-
Disease Prediction Using Ensemble Learning Models: A Comprehensive Approach
Abstract: In recent years, ensemble learning techniques have become pivotal in advancing predictive analytics within healthcare, particularly for early disease detection. The inherent variability and complexity of medical data, often characterized by high dimensionality, class imbalance, and noise, make it challenging for standalone classifiers to maintain high predictive accuracy. Ensemble learning, by integrating multiple models through bagging, boosting, or stacking, offers a more robust and generalizable approach. This study explores the …
Published in Journal of Communication Engineering & Systems · Vol. 15, Issue 3, 2025 · pp. 26–33 Read article
-
Evaluating the Efficiency of LLMs-SA (Sentiment Analysis) via Social Media Texts
Abstract: Sentiment analysis (SA) is becoming popular in business and scientific communities as the processing of natural language (NLP), computational linguistics, text analytics, image-based processing or video- based processing is used in extracting and mining subjective information in the web, social network, etc. It is able to detect positive, negative or neutral information and can be selected to absorb polarity, sentiments, urgency and goals of mount importance. The majority of the …
Published in Journal of Computer Technology & Applications · Vol. 16, Issue 3, 2025 Read article
-
ML-Enhanced Smart Sensing Framework for IoT- Based Structural Health Monitoring Using Conductive Polymer Composites
Abstract: The growing demand for intelligent structural health monitoring (SHM) in dynamic infrastructures necessitates flexible sensing systems that are not only mechanically robust but also capable of real-time interpretation. Conventional SHM frameworks often rely on brittle sensor configurations and cloud-dependent processing pipelines, which suffer from latency, limited durability, and poor adaptability under variable loading conditions. Despite recent advances in composite materials and machine learning, current approaches lack a unified framework that …
Published in Journal of Polymer & Composites · Vol. 13, Issue 6, 2025 · pp. 348–369 Read article